A Caltech Library Service

Combining Generative Models and Fisher Kernels for Object Recognition

Holub, Alex D. and Welling, Max and Perona, Pietro (2005) Combining Generative Models and Fisher Kernels for Object Recognition. In: Proceedings of the Tenth IEEE International Conference on Computer Vision, 2005. ICCV 2005. Vol.1. IEEE , Piscataway, NJ, pp. 136-143. ISBN 0-7695-2334-X.

[img] PDF - Published Version
See Usage Policy.

[img] PDF - Submitted Version
See Usage Policy.


Use this Persistent URL to link to this item:


Learning models for detecting and classifying object categories is a challenging problem in machine vision. While discriminative approaches to learning and classification have, in principle, superior performance, generative approaches provide many useful features, one of which is the ability to naturally establish explicit correspondence between model components and scene features – this, in turn, allows for the handling of missing data and unsupervised learning in clutter. We explore a hybrid generative/discriminative approach using ‘Fisher kernels’ [1] which retains most of the desirable properties of generative methods, while increasing the classification performance through a discriminative setting. Furthermore, we demonstrate how this kernel framework can be used to combine different types of features and models into a single classifier. Our experiments, conducted on a number of popular benchmarks, show strong performance improvements over the corresponding generative approach and are competitive with the best results reported in the literature.

Item Type:Book Section
Related URLs:
URLURL TypeDescription
Perona, Pietro0000-0002-7583-5809
Additional Information:© 2005 IEEE.
Record Number:CaltechAUTHORS:20160929-121610328
Persistent URL:
Official Citation:A. D. Holub, M. Welling and P. Perona, "Combining generative models and Fisher kernels for object recognition," Tenth IEEE International Conference on Computer Vision (ICCV'05) Volume 1, 2005, pp. 136-143 Vol. 1. doi: 10.1109/ICCV.2005.56
Usage Policy:No commercial reproduction, distribution, display or performance rights in this work are provided.
ID Code:70661
Deposited By: SWORD User
Deposited On:04 Oct 2016 03:28
Last Modified:11 Nov 2021 04:33

Repository Staff Only: item control page